Triple
T528027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lysgårdsbakken |
E10966
|
entity |
| Predicate | hasComponent |
P35
|
FINISHED |
| Object |
K-90 hill
K-90 hill is the normal hill ski jumping slope at the Lysgårdsbakken ski jumping arena in Lillehammer, Norway.
|
E67398
|
NE FINISHED |
How this triple was built (4 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: K-90 hill | Statement: [Lysgårdsbakken, hasComponent, K-90 hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K-90 hill Context triple: [Lysgårdsbakken, hasComponent, K-90 hill]
-
A.
K-123 hill
K-123 hill is the large ski jumping hill at the Lysgårdsbakken ski jumping arena in Lillehammer, Norway, used for major international competitions.
-
B.
Murahwa Hill
Murahwa Hill is a prominent historical and archaeological site near Mutare, Zimbabwe, known for its ancient rock shelters, rock art, and cultural significance to local communities.
-
C.
Cocos Ridge
Cocos Ridge is a prominent submarine volcanic ridge in the eastern Pacific Ocean formed by hotspot-related volcanism on the Cocos Plate.
-
D.
Snake Hill
Snake Hill is a prominent hill in Wuhan, China, known as the historic site on which the famous Yellow Crane Tower stands.
-
E.
Redding Ridge
Redding Ridge is a small village and residential community within the town of Redding in Fairfield County, Connecticut.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: K-90 hill Triple: [Lysgårdsbakken, hasComponent, K-90 hill]
Generated description
K-90 hill is the normal hill ski jumping slope at the Lysgårdsbakken ski jumping arena in Lillehammer, Norway.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: K-90 hill Target entity description: K-90 hill is the normal hill ski jumping slope at the Lysgårdsbakken ski jumping arena in Lillehammer, Norway.
-
A.
K-123 hill
K-123 hill is the large ski jumping hill at the Lysgårdsbakken ski jumping arena in Lillehammer, Norway, used for major international competitions.
-
B.
Murahwa Hill
Murahwa Hill is a prominent historical and archaeological site near Mutare, Zimbabwe, known for its ancient rock shelters, rock art, and cultural significance to local communities.
-
C.
Cocos Ridge
Cocos Ridge is a prominent submarine volcanic ridge in the eastern Pacific Ocean formed by hotspot-related volcanism on the Cocos Plate.
-
D.
Snake Hill
Snake Hill is a prominent hill in Wuhan, China, known as the historic site on which the famous Yellow Crane Tower stands.
-
E.
Redding Ridge
Redding Ridge is a small village and residential community within the town of Redding in Fairfield County, Connecticut.
- F. None of above. chosen
Provenance (5 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1d2851c81908129f7da932ab7b3 |
completed | Feb. 28, 2026, 1:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4c66d76588190864ac6a992c44545 |
completed | March 1, 2026, 11:06 p.m. |
| NEDg | Description generation | batch_69a4c7d8ba3081909ae63cafc11ad6bb |
completed | March 1, 2026, 11:12 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4c83437ec8190a8b71e45357b4e32 |
completed | March 1, 2026, 11:13 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.